A multi-label CNN model for the automatic detection and segmentation of gliomas using [¹⁸F]FET PET imaging

The aim of this study was to develop a convolutional neural network (CNN) for the automatic detection and segmentation of gliomas using [¹⁸F]fluoroethyl-L-tyrosine ([¹⁸F]FET) PET.

Ninety-three patients (84 in-house/7 external) who underwent a 20-40-min static [¹⁸F]FET PET scan were retrospectively included. Lesions and background regions were defined by two nuclear medicine physicians using the MIM software, such that delineations by one expert reader served as ground truth for training and testing the CNN model, while delineations by the second expert reader were used to evaluate inter-reader agreement. A multi-label CNN was developed to segment the lesion and background region while a single-label CNN was implemented for a lesion-only segmentation. Lesion detectability was evaluated by classifying [¹⁸F]FET PET scans as negative when no tumor was segmented and vice versa, while segmentation performance was assessed using the dice similarity coefficient (DSC) and segmented tumor volume. The quantitative accuracy was evaluated using the maximal and mean tumor to mean background uptake ratio (TBR_max/TBR_mean). CNN models were trained and tested by a threefold cross-validation (CV) using the in-house data, while the external data was used for an independent evaluation to assess the generalizability of the two CNN models.

Based on the threefold CV, the multi-label CNN model achieved 88.9% sensitivity and 96.5% precision for discriminating between positive and negative [¹⁸F]FET PET scans compared to a 35.3% sensitivity and 83.1% precision obtained with the single-label CNN model. In addition, the multi-label CNN allowed an accurate estimation of the maximal/mean lesion and mean background uptake, resulting in an accurate TBR_max/TBR_mean estimation compared to a semi-automatic approach. In terms of lesion segmentation, the multi-label CNN model (DSC = 74.6 ± 23.1%) demonstrated equal performance as the single-label CNN model (DSC = 73.7 ± 23.2%) with tumor volumes estimated by the single-label and multi-label model (22.9 ± 23.6 ml and 23.1 ± 24.3 ml, respectively) closely approximating the tumor volumes estimated by the expert reader (24.1 ± 24.4 ml). DSCs of both CNN models were in line with the DSCs by the second expert reader compared with the lesion segmentations by the first expert reader, while detection and segmentation performance of both CNN models as determined with the in-house data were confirmed by the independent evaluation using external data.

The proposed multi-label CNN model detected positive [¹⁸F]FET PET scans with high sensitivity and precision. Once detected, an accurate tumor segmentation and estimation of background activity was achieved resulting in an automatic and accurate TBR_max/TBR_mean estimation, such that user interaction and potential inter-reader variability can be minimized.